Analysis of Day Ahead Electrical Load Forecasting for Uttarakhand using Artificial Neural Network

Abstract

Uttarakhand state of India was formed in the year 2000 and simultaneously power sector was unbundled from state electricity board to power generation, transmission, and distribution utilities. Previous years Tariff Orders clearly indicate that Uttarakhand is becoming energy surplus state to energy deficit state from its inception. Despite repeated guidelines from state power regulator, state power utilities need to use more smart technologies and accurate short-term electrical load forecasting in consideration with weather and other parameters for predicting system load with a leading time of one hour to 24 hours, which is necessary for adequate scheduling and operation of power systems. It will also help for working of their electrical infrastructure efficiently, securely, and economically. This paper describes 24-hour-ahead load prediction whose results will give day ahead load forecast for the future day. Artificial Neural Networks is used for creating such algorithm. The ANN is a tool that duplicates the idea of the person’s brain. The ANN is designed and skilled to receive past load and climate information like temperature, humidity, wind speed, precipitation, pressure, and irradiance as input and after calculating correlation between load and meteorological parameters and load and days to get optimized inputs which produce load forecast as its output. ANN provides predicted load with minimum error and Mean Absolute Percent Error (MAPE) is calculated. Considering this work to use such type of short-term scheduling, short term power purchase process and its related suggestions may help state to be profit making organization and make state energy surplus again.